Analysis from KeRank: From kernels to backup genes.

Kernelization section

The algorithm transformed the semantic similarity matrix to make it compatible with a kernel. Once this was done for each network and kernel type, it was integrated by kernel type. Below is a general analysis of the properties of each matrix in the different phases of the process.

Matrix properties

Net Matrix_Dimensions Matrix_Elements Matrix_Elements_Non_Zero
small_pro 200x200 40000 40000
small_pro_two 200x200 40000 40000
Net Kernel Matrix_Dimensions Matrix_Elements Matrix_Elements_Non_Zero
small_pro rf 200x200 40000 40000
small_pro_two rf 200x200 40000 40000
small_pro ct 200x200 40000 40000
small_pro_two ct 200x200 40000 40000
Integration Kernel Matrix_Dimensions Matrix_Elements Matrix_Elements_Non_Zero
mean rf 200x200 40000 40000
mean ct 200x200 40000 40000

Weight values

Ranker section